Arxiv:1910.09700 Autotrain compatible Conversational Endpoints compatible Llama Region:us Safetensors
SmolLM 135M Layer Pruned 90M Raw Benchmarks
nn.n% — How the model compares to the reference models: Anthropic Sonnet 3.5 ("so35"), GPT-4o ("gpt4o") or GPT-4 ("gpt4").
What is the LLM Explorer Rank (Score)
SmolLM 135M Layer Pruned 90M Raw Parameters and Internals
| LLM Name | SmolLM 135M Layer Pruned 90M Raw |
| Repository 🤗 | https://huggingface.co/Trelis/SmolLM-135M-layer-pruned-90M-raw |
| Model Size | 135m |
| Required VRAM | 0.2 GB |
| Updated | 2024-11-07 |
| Maintainer | Trelis |
| Model Type | llama |
| Model Files | |
| Model Architecture | LlamaForCausalLM |
| Context Length | 2048 |
| Model Max Length | 2048 |
| Transformers Version | 4.44.2 |
| Tokenizer Class | GPT2Tokenizer |
| Padding Token | <|im_end|> |
| Vocabulary Size | 49152 |
| Torch Data Type | bfloat16 |
Best Alternatives to SmolLM 135M Layer Pruned 90M Raw
Best Alternatives |
Context / RAM |
Downloads |
Likes |
|---|---|---|---|
| SmolLM2 135M Instruct | 8K / 0.3 GB | 4861 | 48 |
| SmolLM2 135M | 8K / 0.3 GB | 3852 | 23 |
| SmolLM2 Prompt Enhance | 8K / 0.5 GB | 32 | 4 |
| SmolLM2 135M | 8K / 0.3 GB | 226 | 0 |
| SmolLM2 135M Instruct | 8K / 0.3 GB | 42 | 0 |
| SmolLM 135M | 2K / 0.5 GB | 43741 | 170 |
| SmolLM 135M Instruct | 2K / 0.3 GB | 26856 | 95 |
| AMD Llama 135M | 2K / 0.5 GB | 11754 | 110 |
| ... Instruct Layer Pruned 90M Raw | 2K / 0.2 GB | 255 | 1 |
| AMD Llama 135M Code | 2K / 0.5 GB | 1282 | 12 |
Note: green Score (e.g. "73.2") means that the model is better than Trelis/SmolLM-135M-layer-pruned-90M-raw .
Rank the SmolLM 135M Layer Pruned 90M Raw Capabilities
🆘 Have you tried this model? Rate its performance. This feedback would greatly assist ML community in identifying the most suitable model for their needs. Your contribution really does make a difference! 🌟
What open-source LLMs or SLMs are you in search of? 37617 in total.
Original data from HuggingFace, OpenCompass and various public git repos.
Release v2024072803